The DOI matches its Crossref record; 117 of the 131 references it cites were found in a registry or an index; 33 of the 83 sources its claims cite were checked for support.
The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective
Open accessAbstract
Image-based navigation is widely considered the next frontier of minimally invasive surgery. It is believed that image-based navigation will increase the access to reproducible, safe, and high-precision surgery as it may then be performed at acceptable costs and effort. This is because image-based techniques avoid the need of specialized equipment and seamlessly integrate with contemporary workflows. Furthermore, it is expected that image-based navigation techniques will play a major role in enabling mixed reality environments, as well as autonomous and robot-assisted workflows. A critical component of image guidance is 2D/3D registration, a technique to estimate the spatial relationships between 3D structures, e.g., preoperative volumetric imagery or models of surgical instruments, and 2D images thereof, such as intraoperative X-ray fluoroscopy or endoscopy. While image-based 2D/3D registration is a mature technique, its transition from the bench to the bedside has been restrained by well-known challenges, including brittleness with respect to optimization objective, hyperparameter selection, and initialization, difficulties in dealing with inconsistencies or multiple objects, and limited single-view performance. One reason these challenges persist today is that analytical solutions are likely inadequate considering the complexity, variability, and high-dimensionality of generic 2D/3D registration problems. The recent advent of machine learning-based approaches to imaging problems that, rather than specifying the desired functional mapping, approximate it using highly expressive parametric models holds promise for solving some of the notorious challenges in 2D/3D registration. In this manuscript, we review the impact of machine learning on 2D/3D registration to systematically summarize the recent advances made by introduction of this novel technology. Grounded in these insights, we then offer our perspective on the most pressing needs, significant open problems, and possible next steps.
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
This systematic review and perspective examines how machine learning has been applied to image-based 2D/3D registration for image-guided interventions, reviewing 48 studies published from January 2012 through February 2021. It finds promising improvements in capture range, representation learning, and direct pose regression, but persistent gaps in domain shift, multi-object registration, verification/uncertainty, and standardized evaluation.
Key findings
- Across 48 included studies, most addressed X-ray to CT/CBCT registration (34), followed by X-ray to 3D object models (10); clinical applications included orthopedics (19), angiography (9), radiation therapy (7), and cephalometry (4).
- The review identified five machine learning themes: contextualization (14 studies), representation learning (12), similarity modeling (10), direct parameter regression (22), and verification (4). Most methods were single-object: 45 of 48 studies considered only one object, and the few multiple-object methods solved objects independently.
- Training data were often synthetic: 16 of 48 studies used real clinical or cadaveric data to train, while among 32 deep learning studies, 24 trained on synthetic data, 7 on real data, and 1 used a pretrained network. Seven studies comparing synthetic and real performance found substantial drops under domain shift, and ten synthetic-trained studies never meaningfully tested on real data.
- The authors conclude that machine learning has improved capture range and enabled fast direct regression, but ambiguity, high-dimensional optimization, verification/uncertainty, multi-object and foreign-object handling, and generalizability remain open problems requiring standardized metrics, public benchmarks, and more generalist components.
Methods
- PRISMA systematic review searched PubMed, embase, Business Source Ultimate, and Compendex for January 2012–February 2021 using 2D/3D registration terms combined with learning/training/testing terms; 559 records were found, 495 unique studies screened, 447 excluded, and 48 included for full-text review.
- Five authors extracted data using a template covering method summary, modalities and registration phase, spatial transformation, machine learning model and training setup, evaluation strategy including domain shift, and methodological concerns; each article was coded by at least two authors, with one author merging reports into a consensus document.
- The paper synthesizes findings narratively around five themes and a perspective discussion, without a quantitative meta-analysis.
Limitations
- Stated in the paper: the search may not be exhaustive because it omitted newer or less popular terminology such as “pose regression” and modality-specific terms such as “video to CT registration”; it may have excluded studies not explicitly characterized as machine/deep learning or from the general computer vision literature; and it was limited to published manuscripts, so publication bias may have excluded relevant work.
- Evident from the text: the review is qualitative and narrative rather than meta-analytic, and the included studies use heterogeneous metrics, datasets, and evaluation protocols, with many relying on synthetic data and few reporting real-data performance, which limits comparability and real-world conclusions; the authors also note that private code and datasets inhibit reproducibility.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures
Verification
Claims the paper makes
88 Own interpretation · 63 No basis given · 40 Own result · 30 Not checked yet · 14 Partly supported · 12 No full text of the sources · 6 Sources not found · 5 Supported so far · 2 Mixed support · 1 Supported · 1 Not supported · 1 Own method · accuracy not yet measured
Some cited sources support this claim and some don’t — read each source’s verdict below.
In the paper
“However, we found that each of the contextualization studies which considered multiple objects (Grupp et al., 2020c; Doerr et al., 2020; Wang et al., 2020; Esfandiari et al., 2021) did not explicitly isolate the parameters corresponding to each object, but instead used a single NN with data in the output layer indexed according to the appropriate object.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.3 Registration of Multiple Objects, Compound or Non-rigid Motion, and Presence of Foreign Objects
What the sources say
- Disputedcites Grupp et al., 2020c sourceExperimental — accuracy not yet measured
The Materials and Methods section (Intraoperative Registration Strategy; page unavailable) describes successive optimizations of individual objects, followed by simultaneous optimization of their poses. It also specifies different optimization parameters for the pelvis than for the femur and fragment. This contradicts the attribution that the study did not isolate object-specific parameters and instead used a single neural network with object-indexed outputs. (LLM, conf=0.90)
Checked by a reasoning model — may be wrong.
- Partly supportedcites Doerr et al., 2020 sourceExperimental — accuracy not yet measured
The Methods section (page unavailable) describes one Faster R-CNN that handles multiple regions of interest, and the Discussion says the training images contained two screws. That supports the shared-network, multiple-object part of the claim. The Methods describe outputs per region of interest and bounding-box coordinates by class, however, not an output layer explicitly indexed by individual object. (LLM, conf=0.83)
- Partly supportedcites Wang et al., 2020 sourceExperimental — accuracy not yet measured
Section 3.1.3 describes tracking points with a pseudo-Siamese network to reproduce the pose of each bone, supporting the characterization of this as a multiple-object registration study. Section 3.2 says the network outputs tracked image points, but does not establish that its output layer is indexed by bone or that parameters are not isolated by object. Its branches are described by image source, not by object. (LLM, conf=0.78)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Disputed
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“and perhaps worst, ten studies that trained on synthetic data never even tested (meaningfully) on real data (Hou et al., 2017, 2018; Pei et al., 2017; Xie et al., 2017; Bier et al., 2018; Foote et al., 2019; Guan et al., 2019; Yang and Chen, 2019; Neumann et al., 2020; Zhang et al., 2020).”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.1 Preserving Improvements Under Domain Shift From Training to Deployment
What the sources say
- Disputedcites Hou et al., 2017 sourceExperimental — accuracy not yet measured
For the cited Hou et al. (2017) study, the Experiments and Results section (pp. 5–6) explicitly reports testing on a real-world set of 34 fetal brain MRI scans and gives a prediction-error result. It also describes an experiment using motion-corrupted fetal MRI slices to test the method under real conditions. The paper therefore contradicts the claim that this study never meaningfully tested on real data; it cannot establish what the other nine cited studies did. (LLM, conf=0.88)
Checked by a reasoning model — may be wrong.
- Not checked — no full text of the sourcecites Pei et al., 2017 source
- Not checked — no full text of the sourcecites Xie et al., 2017 source
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Disputed
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Machine learning methods, including deep neural networks (NNs), have enjoyed a growing popularity across a variety of image analysis problems (Vercauteren et al., 2019), precisely because they do not require explicit definitions of complex functional mappings.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 1 Introduction > 1.2 Problem Formulation
What the sources say
- Partly supportedcites Vercauteren et al., 2019 sourceExperimental — accuracy not yet measured
The Introduction describes machine learning across multiple computer-assisted intervention tasks, and the Intelligent Imaging in Interventional Biophotonics section notes its increasing use in hyperspectral imaging. The Contextual Learning for Image Registration section gives an example of data-driven methods that avoid explicitly modeling image-intensity correlations. That example does not establish that avoiding explicit definitions of complex functional mappings is the general reason for machine learning’s growing popularity across image analysis. (LLM, conf=0.84)
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“Conventional intensity-based methods mostly use hand-crafted similarity metrics between y v and its current best estimate y^v=(P(Kv,Txv)◦DωD)(x)fx1 as loss function. Common choices for the similarity metric are Normalized Cross Correlation (NCC), gradient information (Berger et al., 2016), or Mutual Information (MI) (Maes et al., 1997).”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 1 Introduction > 1.2 Problem Formulation
What the sources say
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“The aforementioned complexity also leads to registration ambiguity, which is most pronounced in single-view registration (Otake et al., 2013; Uneri et al., 2013).”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 1 Introduction > 1.2 Problem Formulation
What the sources say
- Partly supportedcites Otake et al., 2013 sourceExperimental — accuracy not yet measured
The Introduction describes registration becoming ill-posed under anatomical deformation, with local optima and insensitivity to out-of-plane translation. The Discussion says the analysis used an AP projection view, but the paper does not establish that ambiguity is *most pronounced* in single-view registration compared with multiview registration. Page numbers were not available in our copy. (LLM, conf=0.84)
- Supportedcites Uneri et al., 2013 source
The Results (§3.1; page not provided) report that target registration error is highest near Δθ = 0°, the single-view condition, because depth resolution is limited. Error falls rapidly when the projection views have even a small angular separation. (LLM, conf=0.92)
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“While, indeed, analytical solutions now exist to precisely recover 2D/3D spatial relations under certain conditions (Markelj et al., 2012; Uneri et al., 2013; Gao et al., 2020b; Grupp et al., 2020b), several hard challenges prevail.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 1 Introduction > 1.1 Background
What the sources say
- Not checked — no full text of the sourcecites Markelj et al., 2012 source
- Partly supportedcites Uneri et al., 2013 sourceExperimental — accuracy not yet measured
The Discussion reports precise 3D localization under specified projection-angle conditions (TRE <2 mm at about 10° separation). But Methods §2.1 describes an iterative optimization algorithm, not an analytical solution for recovering the 2D/3D spatial relationship. The analytically exact calculation mentioned in Methods §2.1.2 concerns a projection line integral, not the registration solution. (LLM, conf=0.88)
- Not matchedcites Gao et al., 2020b
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Indeed, among the seven studies that trained deep CNNs on synthetic data and evaluated in a way that allowed for comparisons between synthetic and real data performance, we found quite substantial performance drops (Miao et al., 2018; Bier et al., 2019; Gao et al., 2020c; Doerr et al., 2020; Gu et al., 2020; Guan et al., 2020; Li et al., 2020).”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.1 Preserving Improvements Under Domain Shift From Training to Deployment
What the sources say
- Partly supportedcites Miao et al., 2018 sourceExperimental — accuracy not yet measured
The Training section says the model used both CBCT-derived X-ray/DRR pairs and additional synthetic pairs. The Testing section and Table 2 report worse results on clinical data than on CBCT data, including a substantial rise in gross failure rate for the single-agent method. But the CBCT evaluation used real X-ray images, not synthetic test data, so this paper does not establish a synthetic-versus-real performance drop as phrased. (LLM, conf=0.86)
- Partly supportedcites Bier et al., 2019 sourceExperimental — accuracy not yet measured
The Experiments and results section says the CNN was trained on synthetic data and evaluated quantitatively on both synthetic and real X-rays. The Synthetic data subsection reports a mean landmark error, and the Clinical data subsection says real-image errors are presented in Table 2, but the passages in our copy do not give those values or establish a substantial overall performance drop. The cited paper also cannot substantiate the citing authors’ count of seven studies. (LLM, conf=0.82)
- Not matchedcites Gao et al., 2020c
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“Other metrics that are not uniquely attributable to a domain include the registration capture range (Schaffert et al., 2019; Esfandiari et al., 2021) and the registration success rate (Varnavas et al., 2013; Mitrovi et al., 2014; Miao et al., 2016b; Yang and Chen, 2019; Schaffert et al., 2020a).”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.2 Experimental Design, Reporting, and Reproducibility
What the sources say
- Supportedcites Schaffert et al., 2019 source
Section 3.3 (p. 9) defines registration capture range as the maximum initial registration error for which at least 95% of registrations succeed. Section 3.4 (p. 9) reports capture-range results. In the citing sentence, Schaffert et al. (2019) is attached to capture range, not success rate. (LLM, conf=0.92)
- Not checked — no full text of the sourcecites Varnavas et al., 2013 source
- Not matchedcites Miao et al., 2016b
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Therefore, applying a synthetic data-trained machine learning model to real data is likely to result in substantially deteriorated performance (Unberath et al., 2018, 2019).”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.1 Preserving Improvements Under Domain Shift From Training to Deployment
What the sources say
- Partly supportedcites Unberath et al., 2018 sourceExperimental — accuracy not yet measured
The Introduction says models trained on conventional DRRs do not generalize to clinical data, and the Task-based Evaluation reports failed landmark predictions on clinical images. But the same evaluation finds that models trained on DeepDRRs—a different form of synthetic data—make accurate predictions on clinical images. The claim overgeneralizes a limitation of conventional synthetic images to synthetic training data as a whole. (LLM, conf=0.88)
- Supportedcites Unberath et al., 2019 source
The Challenges and limitations section (page unavailable) explicitly reports that ConvNets trained on simulated X-ray images performed worse on real data than on synthetic test data. This supports the cited claim in the paper’s X-ray imaging context. (LLM, conf=0.90)
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“Methods which model 2D/3D correspondences (Schaffert et al., 2019, 2020a,b; Liao et al., 2019) will require an additional dimension to handle the assignment of points to various obejcts, adding complexity and potentially increasing the challenges associated with training.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.3 Registration of Multiple Objects, Compound or Non-rigid Motion, and Presence of Foreign Objects
What the sources say
- Supportedcites Schaffert et al., 2019 source
The citation follows “Methods which model 2D/3D correspondences,” identifying Schaffert et al. as an example. The Introduction (p. 2) describes correspondence-based 2-D/3-D registration, and the Conclusion (p. 12) says the paper proposes learning weights for local correspondences. The subsequent prediction about assigning points to multiple objects is the citing authors’ own argument, not a finding attributed to this source. (LLM, conf=0.90)
- Not checked — no full text of the sourcecites Liao et al., 2019 source
plainconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- The authors state this as an assumption: The 2D view modality is X-ray.
- Supported
- It may state two separate claims as one. 82
- Probably not a substantial claim. 76
- The quote only partly states this claim. 1
Some cited sources support this claim and some don’t — read each source’s verdict below.
In the paper
“Image-based navigation techniques do not require specialized equipment but rely on traditional intra-operative imaging that enabled the minimally invasive technique in the first place.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 1 Introduction > 1.1 Background
What the sources say
- Partly supportedcites Nolte et al., 2000 sourceExperimental — accuracy not yet measured
The Discussion says the system uses widely available C-arm fluoroscopy for intraoperative imaging. But the System components section describes an optoelectronic navigator, tracked instruments, and custom software, so the claim that it requires no specialized equipment is not supported. Page numbers are not provided in our copy. (LLM, conf=0.90)
- Not checked — no full text of the sourcecites Mirota et al., 2011 source
- Disputedcites Leonard et al., 2016 sourceExperimental — accuracy not yet measured
The Introduction and Method describe navigation based on endoscopic images registered to a CT scan, supporting the imaging portion of the claim. But the Method says the endoscope’s motion is tracked with a 6DOF magnetic tracker to estimate reconstruction scale, and the Results describe attaching that tracker to the endoscope. This contradicts the claim that the technique requires no specialized equipment. Page numbers were not available in our copy. (LLM, conf=0.88)
Checked by a reasoning model — may be wrong.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“Further, because image-based navigation techniques are designed to seamlessly integrate into conventional surgical workflows, their use should—in theory—not cause frustration or prolonged procedure times (Vercauteren et al., 2019).”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 1 Introduction > 1.1 Background
What the sources say
- Supportedcites Vercauteren et al., 2019 source
In “Navigation and Image Registration Challenges,” the paper says external navigation can increase procedure time and cause surgeon frustration, while image-based registration is widely believed to integrate better with procedural workflow and mitigate those drawbacks. The citing sentence presents this as a theoretical expectation, not an observed outcome. (LLM, conf=0.88)
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“While these metrics are positively correlated with pose differences when the perturbations in {K^v,T^xv,ω^D} are small, they are generally non-convex and fail to accurately represent pose offsets when perturbations are large.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 1 Introduction > 1.2 Problem Formulation
What the sources say
- Not checked — no full text of the sourcecites Berger et al., 2016 source
- Partly supportedcites Maes et al., 1997 sourceExperimental — accuracy not yet measured
The Introduction says correlation of sparse features such as edges and ridges can have a peaked optimum near registration but be insensitive to misregistration at larger distances. The paper does not establish that hand-crafted metrics are generally non-convex or that they fail to represent large pose offsets; its Discussion reports recovering misregistrations as large as 10 degrees and 40 mm. No page numbers are available in our copy. (LLM, conf=0.84)
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Unfortunately, navigation systems are not widely adopted due to, among other things, high purchase price despite limited versatility, increased procedural time and cost, and potential for disruptions to surgical workflows due to line-of-sight occlusions or other system complications (Picard et al., 2014; Joskowicz and Hazan, 2016).”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 1 Introduction > 1.1 Background
What the sources say
- Partly supportedcites Picard et al., 2014 sourceExperimental — accuracy not yet measured
Split into 2 atoms — 0 confirmed, 2 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
- Not checked — no full text of the sourcecites Joskowicz and Hazan, 2016 source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“To this end, we conducted a systematic literature review in accordance with the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) method (Moher et al., 2009) (cf. Figure 2).”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.1 Search Methodology
What the sources say
- Partly supportedcites Moher et al., 2009 sourceExperimental — accuracy not yet measured
The PRISMA statement section identifies the cited work as the source of PRISMA’s checklist and flow diagram. It says their aim is to improve the reporting of systematic reviews, not to provide a method for conducting one. The citation supports the identification of PRISMA but not the description of it as a review-conduct method. (LLM, conf=0.84)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
- Partly supported
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“The error metrics that were used included the standard registration pose error (commonly separated into translational and rotational DoFs), keypoint distances (Chou and Pizer, 2014; Zhang et al., 2020), and the mean target registration error (mTRE) in 3D, and varied other metrics in 2D, such as reprojection distances (Bier et al., 2019), segmentation or overlap DICE score (Zhang et al., 2020), or”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.2 Experimental Design, Reporting, and Reproducibility
What the sources say
- Not checked — no full text of the sourcecites Chou and Pizer, 2014 source
- Not checked — no full text of the sourcecites Zhang et al., 2020 source
- Supportedcites Bier et al., 2019 source
Split into 2 atoms — 2 confirmed, 0 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“We found that only three studies in our review register multiple objects through learning-based approaches (Varnavas et al., 2013, 2015b; Wang et al., 2020), and moreover, these studies independently registered single objects in order to obtain relative poses.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.3 Registration of Multiple Objects, Compound or Non-rigid Motion, and Presence of Foreign Objects
What the sources say
- Not checked — no full text of the sourcecites Varnavas et al., 2013 source
- Not matchedcites Varnavas et al., 2015b
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Supportedcites Wang et al., 2020 source
Section 3.1.1 states that each knee bone is registered as a separate 2D–3D procedure, and Section 3.1.3 describes the learning-based network used to recover each bone’s pose for measuring knee-joint motion. Wang et al. is therefore an example of the approach described. The count of three studies is the citing authors’ finding about their review, not a finding attributed to Wang et al. (LLM, conf=0.90)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“To this end, our group has previously released a relatively large dataset of CTs and >350 X-rays across multiple viewpoints of six cadaveric specimens prior to undergoing periacetabular osteotomy (cf. Figure 4) (Grupp et al., 2020).”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.2 Experimental Design, Reporting, and Reproducibility
What the sources say
- Partly supportedcites Grupp et al., 2020 sourceExperimental — accuracy not yet measured
The Materials and Methods (Simulation Study; page unavailable) reports CT scans from six cadaveric specimens and simulated fluoroscopic images from multiple views. The Cadaver Study describes collected intraoperative fluoroscopy, but our copy does not establish that the authors released a dataset containing more than 350 pre-osteotomy X-rays; it identifies only a supplementary video as available with the paper. (LLM, conf=0.85)
plainn = 6- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Although Grupp et al. (2020c) registered multiple objects, the regularization function employed learned landmark annotations from a only a single object.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.3 Registration of Multiple Objects, Compound or Non-rigid Motion, and Presence of Foreign Objects
What the sources say
- Partly supportedcites Grupp et al., 2020c sourceExperimental — accuracy not yet measured
The Materials and Methods section describes multi-object registration, supporting the first part of the claim. It describes regularization of pose parameters, not the use of learned landmark annotations; the landmark used to initialize pelvis registration was manually annotated. Page numbers are unavailable in our copy. (LLM, conf=0.88)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“For example, evaluation on synthetic data may include data sampled from a broad range of viewpoints or deformations that are approximately uniformly distributed. Real data, on the other hand, is not uniformly sampled from such a distribution, but rather, will be clustered around certain viewpoints (see (Grupp et al., 2020c) for a visualization of viewpoints used during a cadaveric surgery vs the”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.2 Experimental Design, Reporting, and Reproducibility
What the sources say
- Partly supportedcites Grupp et al., 2020c sourceExperimental — accuracy not yet measured
The Materials and Methods sections describe simulated views generated from a perturbed AP view and random C-arm rotations, and fluoroscopic views collected during cadaver surgeries (pages unavailable in our copy). They support the distinction between simulated and surgical viewpoints, but do not establish that the simulated viewpoints were approximately uniformly distributed or that the real viewpoints clustered around particular angles. The stated uniform sampling in the simulation passage concerns landmark-offset directions, not viewpoints. (LLM, conf=0.78)
- Partly supportedcites Bier et al., 2019 sourceExperimental — accuracy not yet measured
The Data generation section describes synthetic X-rays generated across a broad range of viewing angles, and the Synthetic data results evaluate detection across viewing directions. It does not say those angles were sampled approximately uniformly or that real surgical images cluster around particular viewpoints; it also does not address deformations. Page numbers are unavailable in our copy. (LLM, conf=0.83)
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Finally, we note that registration uncertainties have the potential to augment existing robotic control methods which rely on intermittent imaging (Alambeigi et al., 2019).”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.4 Estimating Uncertainty and Assuring Quality
What the sources say
- Partly supportedcites Alambeigi et al., 2019 sourceExperimental — accuracy not yet measured
The Problem Formulation models uncertainty in image-derived position estimates as measurement noise, and the Conclusion proposes extending SCADE to real-time control. The paper also uses intermittent images, but it does not specifically propose using registration uncertainties to augment existing robotic control methods. (LLM, conf=0.79)
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Some of these approaches report interval estimates, either by reformulating the registration objective function as a probability distribution and drawing samples (Risholm et al., 2013; Le Folgoc et al., 2016; Schultz et al., 2018), approximating the sampling process using test-time NN drop-out (Yang et al., 2017) or sampling using the test-time deformation covariance matrices embedded within a”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.4 Estimating Uncertainty and Assuring Quality
What the sources say
- Supportedcites Risholm et al., 2013 source
The Methods section (2.3, page not available) says the approach draws samples from a posterior distribution over deformations and uses them to characterize uncertainty. It explicitly describes conveying a confidence interval with the interquartile range. The Discussion equates uncertainty in that posterior with, in deterministic terms, the landscape of the registration objective function. The drop-out and variational-autoencoder methods are attributed to other citations, not Risholm et al. (LLM, conf=0.91)
- Partly supportedcites Yang et al., 2017 sourceExperimental — accuracy not yet measured
The Methods section (2.2.2, page unavailable) says dropout remains enabled at test time to sample multiple predictions, and that the resulting deformation-field variance estimates uncertainty. The Results section (3.1, page unavailable) reports a variance-based uncertainty map, not interval estimates. The other sampling approaches in the citing sentence are attributed to other sources. (LLM, conf=0.85)
- Partly supportedcites Dalca et al., 2019 sourceExperimental — accuracy not yet measured
Section 2.2 (p. 3) describes a network that outputs deformation-related mean and covariance parameters, and Section 4.4.4 (p. 11) shows sampled velocity fields and their empirical variance. But Section 2.4 (p. 5) says the covariance is not used at test time and uncertainty analysis is beyond the paper’s scope. The source therefore supports covariance-based sampling as a capability, not the attributed reporting of interval estimates from test-time sampling. (LLM, conf=0.88)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Supported
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The remaining 48 articles were included for an in-depth full text review, analysis, and data extraction, which was performed by five of the authors (MU, CG, MJ, YH, and RG).”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.1 Search Methodology
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The initial search resulted in 559 records, and after removal of duplicates, 495 unique studies were included for screening.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.1 Search Methodology
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one. The quote only partly states this claim.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Other modality combinations included 2D RGB to 3D CT (2) and 3D MR (1), or did not specify the 3D modality (1).”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.3 Concise Summary of the Overall Trends
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“This is further emphasized by the fact that many studies are only evaluated on synthetic data (which we fear may have sometimes been generated by sampling the PCA model also used for registration, introducing inverse crime) and may not have paired 3D data for extensive quantitative evaluation.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.5 Representation Learning
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“As noted in Section 2.5, most methods here limit themselves to shape estimation and assume that a global rigid alignment is either performed prior or unnecessary.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.7 Direct Parameter Regression
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Two other studies that deal with multiple objects, however, are limited to object detection (Doerr et al., 2020) and inpainting (Esfandiari et al., 2021), respectively, and do not report registration results.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.3 Concise Summary of the Overall Trends
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“The remaining study (Grupp et al., 2020c) performs a 2D segmentation of multiple bones, but does not apply any additional learning to perform the registration.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.3 Concise Summary of the Overall Trends
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Finally, Mitrovi et al. (2014) compare a registration estimate to known local minima and thresholds to determine success/failure, which worked well but may be limited in practice as the approach seems to assume knowledge of the correct solution.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.8 Verification
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Several methods describe innovative learning-based similarity metrics that better reflect distances in geometric parameter space, while other studies present (semi-)global initialization or regularization techniques which may rely on contextual data.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Luo et al. (2019) identify and reject poor quality frames in bronchoscopy”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.4 Contextualization
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Methods directed at cephalometry (Li et al., 2020; Zhang et al., 2018; Pei et al., 2017) are identical in methodology to the radiation therapy methods.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.7 Direct Parameter Regression
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The means to accomplishing this, however, are diverse.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Both methods rely on concepts that are limited to sparse objects, such as vessels.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.6 Similarity Modeling
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Further, we found that most emphasis was given on increasing the capture range of the registration pipeline and very little, if any, attention is paid to increasing the resolution and precision of these metrics.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.6 Similarity Modeling
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“They contribute a non-blind image inpainting method using a FCN that seeks to restore the background anatomy after image regions corresponding to instruments were identified.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.4 Contextualization
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“(Miao et al., 2016a,b, 2018; Zheng et al., 2018). use the image residual between y v and y^v in a region of interest around the projected tool model. Because only a small part of the target image is used, the initialization must be sufficiently close.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.7 Direct Parameter Regression
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Among those, two methods rely on regularization: Grupp et al. (2020c) detect anatomical landmarks to expand an analytic similarity function with landmark-reprojection constraints to enhance the capture range of an intensity-based strategy, while Francois et al. (2020) segment occluding contours to constrain similarity evaluation to salient regions.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.6 Similarity Modeling
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The remaining 14 methods consider rigid parameter regression”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.7 Direct Parameter Regression
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Consequently, these methods rely on population-level models and are thus different from methods used for radiation therapy (Chou et al., 2013; Chou and Pizer, 2013, 2014; Zhao et al., 2014; Foote et al., 2019) and angiography (Brost et al., 2012; Baka et al., 2015), which rely on patient-specific models that are built pre- and intra-operatively, respectively.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.5 Representation Learning
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Neumann et al. (2020) regress the disparity between corresponding points in source and target images to quantify image dissimilarity”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.6 Similarity Modeling
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“To this end, Liao et al. (2019) train a network to establish keypoint correspondences between the source and target images.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.6 Similarity Modeling
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“It is worth mentioning that, while most methods rely on PCA to condense deformable motion parametrizations, it has also been found useful to identify and focus on the primary modes of variation in rigid registration (Brost et al., 2012).”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.5 Representation Learning
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Toth et al. (2018) extract features using a CNN from both source and target image independently and then concatenate them for pose regression using fully connected layers.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.7 Direct Parameter Regression
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“To this end, Gu et al. (2020) and Gao et al. (2020b) estimate the geodesic in Riemannian tangent space between the source and target camera poses, which in an ideal case results in a convex similarity function.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.6 Similarity Modeling
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Methods that rely on the target image only are relatively straight-forward and generally train a standard feed-forward CNN architecture to regress pose on large datasets comprising of multiple independent objects or anatomies.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.7 Direct Parameter Regression
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Some studies included in this theme stand out, in that they are certainly mature and were demonstrated to work well on comparably large amounts of real clinical data, such as (Varnavas et al., 2015b) and (Wu et al., 2016); unfortunately however, these methods are not general purpose as they rely on the registration of multiple objects and the availability of two orthogonal views, respectively.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.8 Verification
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“This enables both, end-to-end learning of Gyθy(y),Gxθx(x) and/or SθS(⋅,⋅) during training as well as analytic gradient-based optimization using backpropagation during application.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.6 Similarity Modeling
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“While all methods for landmark detection rely on deep CNNs”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.4 Contextualization
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We found that all methods included in this review are limited to registration of a single object and it remains unclear how these methods would apply to multiple objects, in part, because of the combinatorial explosion of relative poses.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.7 Direct Parameter Regression
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“PCA is by far the most prevalent method for representation learning and is used in all but one study.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.5 Representation Learning
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In those lower dimensional spaces, e.g., the six parameters of a rigid transformations or the principal components of a PCA model, direct pose regression from the target and/or source images is a clearly established line of research.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Unfortunately, none of the studies reviewed here describes a dedicated effort to establish such a canonical reference frame, suggesting that those methods will eventually hit a performance ceiling that is determined by the misalignment within the reference coordinate systems in the training data.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.7 Direct Parameter Regression
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“We found that representation learning techniques, currently dominated by PCA, are a clearly established tool to reduce the dimensionality of deformable 2D/3D registration problems, and may even be useful for rigid alignment.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“While several methods report an overall improved registration performance when using their novel, machine learning-enhanced algorithms, we did not register any method with a particular focus on reducing ambiguity.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Doerr et al. (2020) describe a deep learning-based alternative, where the Fast R-CNN object detector is re-trained to return bounding boxes of 30 different screw types in varied poses.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.4 Contextualization
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Despite this positive prospect on the utility of machine learning for 2D/3D registration, we noted certain trends and recurring shortcomings in our review that we will discuss next.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“The more obvious examples are visual servoing of novel robotic surgery platforms (Gao et al., 2019) or robotic imaging paradigms that alter how data is acquired (Zaech et al., 2019; Thies et al., 2020).”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.1 Preserving Improvements Under Domain Shift From Training to Deployment
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Indeed, of the 32 studies that describe deep learning-based methods, 24 trained on synthetic data (seven trained on real data, and one did not train at all but used a pre-trained network).”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.1 Preserving Improvements Under Domain Shift From Training to Deployment
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“There are no standard routines to define the successful registrations.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.2 Experimental Design, Reporting, and Reproducibility
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“However, we also believe that the lack of universally accepted reporting guidelines, error metrics, and datasets is a severe shortcoming that has unfortunate consequences, such as a high risk of duplicated efforts and non-interpretable performance reporting.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.2 Experimental Design, Reporting, and Reproducibility
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Further, most code-bases and more importantly datasets are kept private which inhibits reproduction, since re-implementation is particularly prone to biased conclusions.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.2 Experimental Design, Reporting, and Reproducibility
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“While a too strong focus on “winning benchmarks” is certainly detrimental to the creativity of novel approaches, we feel that the lack of public benchmarks for 2D/3D registration and related problems is perhaps an even greater worry.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.2 Experimental Design, Reporting, and Reproducibility
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“An issue that appears to have become more prevalent with the introduction of machine learning methods that are developed and trained on synthetic data is the lack of substantial results on clinically relevant, real data.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.2 Experimental Design, Reporting, and Reproducibility
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“most of those studies are performed “on the benchtop.””
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 4 Conclusion
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Contextualization of data, representation learning to reduce problem dimensionality, similarity modeling for increased capture range, direct pose regression to avoid iterative optimization, as well as confidence assessment are all well established research thrusts, which are geared towards developing automated registration pipelines.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 4 Conclusion
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“These challenges already exist for rigid 2D/3D registration and are further exacerbated in rigid plus deformable registration settings.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 1 Introduction > 1.2 Problem Formulation
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“Surgical navigation promotes reproducibly good patient outcomes, and when combined with robotic assistance systems, may enable novel treatment options and improved techniques (van der List et al., 2016).”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 1 Introduction > 1.1 Background
What the sources say
- Not checked — no full text of the sourcecites van der List et al., 2016 source
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“While image-based 2D/3D registration is a mature technique, its transition from the bench to the bedside has been restrained by well-known challenges, including brittleness with respect to optimization objective, hyperparameter selection, and initialization, difficulties in dealing with inconsistencies or multiple objects, and limited single-view performance.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > Abstract
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Even in the simplest case, 2D/3D registration describes a non-convex optimization problem with at least six DoFs to describe a rigid body transform.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 1 Introduction > 1.2 Problem Formulation
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Rather, they optimize parametric functions, such as convolutional NNs (CNNs), on training data such that the model learns to approximate the desired mapping between input and output variables.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 1 Introduction > 1.2 Problem Formulation
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Perhaps the most straightforward way of verifying a registration result is to visually inspect the 2D overlay of the projected 3D data—this approach, however, is neither quantitative nor does it scale since it is based on human intervention.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 1 Introduction > 1.2 Problem Formulation
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We also did not use modality specific terms, such as “video to CT registration”, which may have excluded some manuscripts that focus on endoscopy or other RGB camera-based modalities.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.2 Limitations
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Despite our efforts to broaden the search terms regarding 2D/3D registration, we acknowledge that the list may not be exhaustive.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.2 Limitations
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Estimating good initial parameters is commonly achieved using some manual interaction, which is cumbersome and time consuming, or—in research papers—neglected all-together.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 1 Introduction > 1.2 Problem Formulation
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Every one of the 48 articles was analyzed and coded by at least two of the five authors and one author (MU) merged the individual reports into a final consensus document.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.1 Search Methodology
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Therefore, these techniques do not introduce economic trade-offs.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 1 Introduction > 1.1 Background
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“While frustrations induced by workflow disruption affect every operator equally, the aforementioned limitations regarding cost particularly inhibit the adoption of surgical navigation systems in geographical areas with less specialized healthcare providers with lower volumes for any procedure; areas where routine use of navigation would perhaps be most impactful.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 1 Introduction > 1.1 Background
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Because we are primarily interested in surveying the impact of contemporary machine learning techniques, such as deep CNNs, on 2D/3D registration, we limit our analysis to records that appeared after January 2012, which pre-dates the onset of the ongoing surge of interest in learning-based image processing (Krizhevsky et al., 2012).”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.1 Search Methodology
What the sources say
- Not matchedcites Krizhevsky et al., 2012
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Publication bias may have resulted in the exclusion of works relevant to this review.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.2 Limitations
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The terminology used in the search may also have resulted in the exclusion of relevant work from the general computer vision literature.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.2 Limitations
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A claim is checked only against the cited paper’s full text, never its abstract, and none is available for its sources.
In the paper
“Its magnitude depends, among other things, on the similarity function as well as the optimizer, and it can be stated quantitatively as the mean target registration error (mTRE) between 3D keypoints at initialization1.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 1 Introduction > 1.2 Problem Formulation
What the sources say
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“Although statistical modeling techniques exist to limit the parameter search space, the registration accuracy and sensitivity to key features remain an area of concern (Zhu et al., 2021).”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 1 Introduction > 1.2 Problem Formulation
What the sources say
- Not checked — no full text of the sourcecites Zhu et al., 2021 source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Rather, it is shackled to the bench top because several hard open challenges inhibit its widespread adoption.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 1 Introduction > 1.2 Problem Formulation
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“One reason these challenges persist today is that analytical solutions are likely inadequate considering the complexity, variability, and high-dimensionality of generic 2D/3D registration problems.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > Abstract
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This is particularly appealing for traditionally time critical applications, such as tumor tracking in radiation therapy.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“While these methods are in a development stage, their flexibility may prove a great strength in developing solutions that meet clinical needs.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Pose regression directly from images is appealing because it may result in substantially faster convergence, potentially with a single forward pass of a CNN.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.7 Direct Parameter Regression
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“As highlighted in Section 1.2, 2D/3D registration, especially in deformable scenarios, suffers from high dimensional parameter spaces and changes in any one of those parameters are not easily resolved due to limited information which creates ambiguity.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.5 Representation Learning
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“As we established in Section 1.2 for optimization-based 2D/3D registration algorithms, the cost function—or similarity metric—S(⋅, ⋅) is among the most important components since it will determine parameter updates.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.6 Similarity Modeling
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Further, methods that solely rely on the target image never involve neither the 3D data nor the source images created from it. This may be problematic, because it is unclear how these methods would verify that this specific 2D/3D registration data satisfy, among other things, the canonical coordinate frame assumption.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.7 Direct Parameter Regression
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The demonstrated improvements are generally significant, suggesting huge potential for machine learning in regards to this particular challenge.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Except for few exceptional cases with highly specialized instrumentation, for example (Chou and Pizer, 2013) that relied on on-board CBCT imaging, assumptions around rigid alignment seem to be unjustified, which may suggest that the performance estimates need to be interpreted with care.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.5 Representation Learning
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A claim is checked only against the cited paper’s full text, never its abstract, and none is available for its sources.
In the paper
“This is because image-based navigation techniques (Sugano, 2003; Hummel et al., 2008; Tucker et al., 2018) as well as visual servoing of surgical robots (Yi et al., 2018; Gao et al., 2019; Unberath et al., 2019) will also require high-precision 2D/3D registration at video frame-rates.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective
What the sources say
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“It is well known that most commonly used metrics fail to accurately represent the distances in geometric parameter space that generate the mismatch between the current observations.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.6 Similarity Modeling
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Contextualization, such as landmark detection and segmentation, can mimic user input to enable novel paradigms for initialization while also providing a clear interface for human-computer interaction”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“These approaches supersede optimization with a few forward passes of a machine learning model, which makes them comparably fast.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Methods that regress pose between y v and y^v avoid the aforementioned concern because poses are relative rather than absolute, however similarly to conventional techniques, they require an initialization.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.7 Direct Parameter Regression
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It is undeniable that the introduction of machine learning to contextualize 2D and 3D data enables novel techniques that quite substantially expand the tools one may rely on when designing a 2D/3D registration algorithm, and as such, are likely to become impactful.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.4 Contextualization
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This challenge is mitigated for applications that consider an instrument or tool, because such a canonical system can be readily defined; however, establishing this reference frame is considerably more effortful for patient anatomy and may require (group-wise) 3D/3D registrations.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.7 Direct Parameter Regression
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“Then, compelling evidence will need to be provided on potential sources and extent of algorithmic bias as well as reliable estimates of real world performance (US Food and Drug Administration, 2021).”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.2 Experimental Design, Reporting, and Reproducibility
What the sources say
- Not matchedcites US Food and Drug Administration, 2021
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. It may state two separate claims as one.
- Not matched
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“While experimental conditions, including ground truth targets, are perfectly known for simulation, they are much harder to obtain for clinical or cadaveric data.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.2 Experimental Design, Reporting, and Reproducibility
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“It should be noted, however, that even for this “simple” case to succeed, many conditions must be met including ethical review board approval, digital medicine infrastructure, and methods to reliably annotate the data.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.1 Preserving Improvements Under Domain Shift From Training to Deployment
plainconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“These challenges clearly restrict research, but even more dramatically inhibit translational efforts, simply because we cannot reliably understand whether a specific 2D/3D registration problem should be considered “solved” or what the open problems are.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.2 Experimental Design, Reporting, and Reproducibility
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: unclear — It is unclear whether it could be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Contemporary deep learning-based techniques enable the mapping of very complex functions directly from high-dimensional input data at the cost of heavily over-parameterized models that require as much data as possible to learn sensible associations.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.1 Preserving Improvements Under Domain Shift From Training to Deployment
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“While it is evident that not all evaluation paradigms that are easily available on synthetic data can be readily transferred to clinical data, the reverse is not true.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.2 Experimental Design, Reporting, and Reproducibility
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“A multiple object registration strategy could alternatively parameterize the problem to simultaneously solve for the pose of one object with respect to the imaging device and also for the relative pose between the objects. This approach partially compounds motion of the objects during registration and completely eliminates the possibility of conflicting depth estimates.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.3 Registration of Multiple Objects, Compound or Non-rigid Motion, and Presence of Foreign Objects
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Image-guidance systems often need to process and report information regarding the relative poses between several objects of interest, such as bones, organs and surgical instruments.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.3 Registration of Multiple Objects, Compound or Non-rigid Motion, and Presence of Foreign Objects
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Clearly, this practice is undesirable because 1) synthetic data experiments now cannot serve as a baseline (since they use different metrics and are thus incomparable), and 2) the true quantities of interest remain unknown (for example, a 3D mTRE is more informative than a 2D reprojection TRE since it can adequately resolve depth).”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.2 Experimental Design, Reporting, and Reproducibility
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“For example, in 2D/3D deformable registration for tumor tracking during radiation therapy, accurately recovering the 3D tumor shape and position (quantified well using, e.g., the DICE score of true and estimated 3D position over time) is much more relevant than a Euclidean distance between the deformation field parameters, which would describe irrelevant errors far from the region of interest.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.2 Experimental Design, Reporting, and Reproducibility
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Increasing the rate with which we share code and data will likely result in research that truly advances the contemporary capabilities since the baselines are transparent and much more clearly defined.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.2 Experimental Design, Reporting, and Reproducibility
hedgedconditionaln = 6- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It is evident that data synthesis is an important idea that enables research on creative approaches that contribute to the advancement of 2D/3D registration.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.1 Preserving Improvements Under Domain Shift From Training to Deployment
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
In the paper
“Although representation learning methods may function in the presence of multiple objects without additional modification, better performance is usually obtained by adding structure to account for the known spatial relationships between objects (Yokota et al., 2013).”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.3 Registration of Multiple Objects, Compound or Non-rigid Motion, and Presence of Foreign Objects
What the sources say
- Not matchedcites Yokota et al., 2013
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Indeed, updating an intensity-based registration framework to compute (3) instead of (Eq. 1) is relatively straight forward from an implementation perspective: compute N synthetic radiographs instead of one and perform a pixel-wise sum of the synthetic images together before calculating the image similarity metric, S(⋅, ⋅).”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.3 Registration of Multiple Objects, Compound or Non-rigid Motion, and Presence of Foreign Objects
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- The authors state this as an assumption: The 2D view modality is X-ray.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“An omnipresent concern in the development of machine learning-based components for 2D/3D registration, but everywhere really, is the availability of or access to large amounts of relevant data.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.1 Preserving Improvements Under Domain Shift From Training to Deployment
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Trained machine learning algorithms approximate the target function only on a compact domain (Zhou, 2020), and their behaviour outside this domain is unspecified.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.1 Preserving Improvements Under Domain Shift From Training to Deployment
What the sources say
- Not checked — no full text of the sourcecites Zhou, 2020 source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The wealth of evaluation strategies and metrics can, in part, be attributed to the fact that different clinical applications necessitate different conditions to be met.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.2 Experimental Design, Reporting, and Reproducibility
plainconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Training on synthetic data has clear advantages because large datasets and corresponding annotations can be generated with relatively little effort. In addition, rigid pose and deformation parameters are perfectly known by design thus creating an unbiased learning target.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.1 Preserving Improvements Under Domain Shift From Training to Deployment
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We believe that the lack of new multiple object registration learning-based strategies is indicative of the substantial challenges involved with their development, rather than any perceived lack of the problem’s importance by the community.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.3 Registration of Multiple Objects, Compound or Non-rigid Motion, and Presence of Foreign Objects
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The recent interest in deep learning has brought about a transformational move towards open science, where large parts of the community share their source code publicly and demonstrate the performance of their solutions on public benchmarks, which allows for fair comparisons.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.2 Experimental Design, Reporting, and Reproducibility
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In some cases, the data problem amounts to a simple opportunity cost, e.g., for automation of manually performed tasks such as landmark detection.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.1 Preserving Improvements Under Domain Shift From Training to Deployment
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As representation learning methods have the potential to reconstruct the bony anatomy of joints from a sparse number of 2D views, these could potentially become very popular by enabling navigation to a 3D anatomical model with substantially reduced radiation exposure.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.3 Registration of Multiple Objects, Compound or Non-rigid Motion, and Presence of Foreign Objects
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Although foreign objects such as screws, K-wires, retractors, osteotomes, etc. frequently confound traditional registration methods, their location or poses often have clinical relevance.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.3 Registration of Multiple Objects, Compound or Non-rigid Motion, and Presence of Foreign Objects
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Figure 4 (c) demonstrates that retaining the angled osteotome as a static object in the field of view during performance of the posterior cut helps to guide the flat osteotome along the desired trajectory, but does not guarantee that the acetabular fragment has in fact been freed from the pelvis.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.3 Registration of Multiple Objects, Compound or Non-rigid Motion, and Presence of Foreign Objects
boosteddirectSingle case- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“This is not because specific machine learning models are only suitable for one specific task or anatomy; on the contrary, e.g., pose or PCA component regression techniques are largely identical across clinical targets.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.5 The Need for More Generic Solutions
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“A navigation system capable of accurately tracking the osteotome with respect to the anatomy using a series of oblique views would eliminate the need for additional, “confirmation,” views, potentially reduce operative time, decrease radiation exposure to the patient and clinical team and reduce the frequency of breaches into sensitive anatomy.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.3 Registration of Multiple Objects, Compound or Non-rigid Motion, and Presence of Foreign Objects
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
In the paper
“Methods like (Varnavas et al., 2013; 2015b) rely on patient- and object-specific training sets, and therefore, avoid the task-specificity that comes with one-time training.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.5 The Need for More Generic Solutions
What the sources say
- Not matchedcites Varnavas et al., 2013; 2015b
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Although the oblique views shown in Figure 4 1) and (c) help ensure that the osteotome tip is distinguishable from the acetabulum, the lateral orientation of the tool is challenging to interpret manually and may need to be confirmed by collecting subsequent fluoroscopic views at substantially different orientations, such as the approximate anterior-posterior (AP) view shown in Figure 4 (b).”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.3 Registration of Multiple Objects, Compound or Non-rigid Motion, and Presence of Foreign Objects
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The introduction of machine learning to the 2D/3D pipeline, however, has in a way taken away this generality and methods have become substantially more specialized.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.5 The Need for More Generic Solutions
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Rests on an assumption: Machine learning models have a compact domain assumption that confines solutions to the data domain they were developed on.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Although we have mostly advocated for the development of new uncertainty quantification methods, there is likely still room for improvement of the local/global minima classification problem.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.4 Estimating Uncertainty and Assuring Quality
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“This is perhaps easiest to recognize by first revisiting (1) and noting that registration strategies attempt to find singular solutions, or point estimates, which best minimize the appropriate objective function.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.4 Estimating Uncertainty and Assuring Quality
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“An additional challenge with osteotomy cases is the ability to determine when all osteotomies are complete and the new bone fragment is completely free from its parent.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.3 Registration of Multiple Objects, Compound or Non-rigid Motion, and Presence of Foreign Objects
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“and deep learning has only accelerated and diversified the contributions to the field.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 4 Conclusion
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Due to the interventional nature of most 2D/3D registration applications, care needs to be taken in order to ensure that program runtimes are compatible with intra-operative workflows.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.4 Estimating Uncertainty and Assuring Quality
plainconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it.
In the paper
“However, despite matching random points, this method is likely still scene-specific because matching is performed using a very deep CNN with very large receptive field which may have learned to exploit the global context of the random keypoints, which would not be preserved in different anatomy.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.5 The Need for More Generic Solutions
What the sources say
- Not checked — no full text of the sourcecites Liao et al., 2019 source
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Some frequent properties of these unsolved problems are misleading views with several objects having substantial overlap in 2D, the potential for a varying number of surgical instruments to be present in a view and the existence of objects which are dynamically changing shape or possibly “splitting” into several new objects.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.3 Registration of Multiple Objects, Compound or Non-rigid Motion, and Presence of Foreign Objects
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“Given the computational capacity of contemporary GPUs and sophistication of learning frameworks, it should be feasible to extend the approach of Wu et al. (2016) and pass densely sampled regions of the objective function through a NN, relying on the learning process to extract optimal features for distinguishing local and global minimal.”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 3 Perspective > 3.4 Estimating Uncertainty and Assuring Quality
What the sources say
- Not matchedcites Wu et al., 2016
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Even though learning-based methods show great promise and have supplanted traditional methods in many aspects”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 4 Conclusion
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
The authors state this as an assumption.
The reduction in dimensionality in 2D/3D registration originates from a projective, not an affine, transformation.
“For the purposes of this review, we will assume that the reduction in dimensionality originates from a projective, not an affine, transformation.”
The authors state this as an assumption.
The 2D view modality is X-ray.
“Since the vast majority of studies examined concern 2D X-ray images, we also assume that 2D view modality is X-ray.”
The paper relies on this without support.
New researchers typically spend a great deal of time implementing a traditional registration pipeline.
“New researchers typically spend a great deal of time implementing a traditional registration pipeline so that traditional methods may be leveraged in conjunction with the development of learning-based approaches.”
The paper relies on this without support.
2D/3D registration leads a niche existence.
“2D/3D registration already leads a niche existence”
The paper relies on this without support.
Machine learning models have a compact domain assumption that confines solutions to the data domain they were developed on.
“the compact domain assumption of machine learning models that confine solutions to the data domain they were developed on.”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“conventional optimization methods are prohibitively slow and susceptible to local minima”
From Intraoperative 2D/3D Image Registration via Differentiable X-Ray Rendering (2024) · cites this paper as [52]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“If the initial pose is even a few millimeters from the true pose, these methods can converge to a wrong solution.”
From Intraoperative 2D/3D Image Registration via Differentiable X-Ray Rendering (2024) · cites this paper as [52]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“A major limitation of intensity-based methods is their limited capture range and sensitivity to the initial pose estimate [52].”
From Intraoperative 2D/3D Image Registration via Differentiable X-Ray Rendering (2024) · cites this paper as [52]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.1 Search Methodology
“The remaining 48 articles were included for an in-depth full text review, analysis, and data extraction”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.1 Search Methodology
“Additional twelve studies excluded after full-text review, resulting in a pool of 48 studies included for full review.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.5 Representation Learning
“We identified 12 studies that propose such techniques or use them as part of the registration pipeline”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.5 Representation Learning
“(Brost et al., 2012; Lin and Winey, 2012; Chou and Pizer, 2013, 2014; Chou et al., 2013; Zhao et al., 2014; Baka et al., 2015; Pei et al., 2017; Chen et al., 2018; Zhang et al., 2018; Foote et al., 2019; Li et al., 2020; Zhang et al., 2020).”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.3 Concise Summary of the Overall Trends
“| Miao et al. (2016a) | Siamese CNNs | Synthetic | Realism Tuning | Single | Anatomy | Supervised | Real |”
§ The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective > 2 Systematic Review > 2.3 Concise Summary of the Overall Trends
“| Miao et al. (2016a) | Siamese CNNs | Synthetic | N/A | Single | Anatomy | Supervised | Real |”
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 1×
“the ongoing surge of interest in learning-based image processing [31].”
BackgroundPreferred Reporting Items for Systematic Reviews and Meta-Analyses: the PRISMA statement
Moher, D., Liberati, A., Tetzlaff, J., Altman, D. G., & for the PRISMA Group (2009) · BMJ · doi:10.1136/bmj.b2535 · Cited by 83,823
Preferred reporting items for systematic reviews and meta-analyses: the PRISMA Statement.
(2009) · PubMed Central · Cited by 44,859
On the limited memory BFGS method for large scale optimization
Liu, D. C., & Nocedal, J. M. (1989) · Mathematical Programming · doi:10.1007/bf01589116 · Cited by 9,062
Multimodality image registration by maximization of mutual information
Maes, F., Collignon, A., Vandermeulen, D., Marchal, G., & Suetens, P. (1997) · IEEE Transactions on Medical Imaging · doi:10.1109/42.563664 · Cited by 4,547 · cited 1×
“Common choices for the similarity metric are Normalized Cross Correlation (NCC), gradient information [23], or Mutual Information (MI) [27].”
BackgroundEPnP: An Accurate O(n) Solution to the PnP Problem
Lepetit, V., Moreno-Noguer, F., & Fua, P. (2009) · International Journal of Computer Vision · doi:10.1007/s11263-008-0152-6 · Cited by 3,298
Hansen, N., Müller, S. D., & Koumoutsakos, P. (2003) · Evolutionary Computation · doi:10.1162/106365603321828970 · Cited by 2,601 · cited 1×
“1 using gradient-based or gradient-free methods, such as BFGS [22, 23] or CMA-ES [24] and BOBYQA [25], respectively.”
MethodSurgical skill and complication rates after bariatric surgery
Birkmeyer, J. D., Finks, J. F., O'Reilly, A., Oerline, M., Carlin, A. M., Nunn, A. R., Dimick, J., Banerjee, M., & Birkmeyer, N. J. O. (2013) · New England Journal of Medicine · doi:10.1056/nejmsa1300625 · Cited by 1,504 · cited 2×
“It is well known that due to the aforementioned challenges, among others, outcomes after minimally invasive surgery are positively correlated with technical proficiency, experience, and procedural volume of the operator [1, 2, 3, 4].”
BackgroundTechniques for interpretable machine learning
Du, M., Liu, N., & Hu, X. (2019) · Communications of the ACM · doi:10.1145/3359786 · Cited by 1,268 · cited 1×
“Contextualization, such as landmark detection and segmentation, can mimic user input to enable novel paradigms for initialization while also providing a clear interface for human-computer interaction [81, 82, 83].”
BackgroundThe BOBYQA algorithm for bound constrained optimization without derivatives
Powell, M. J. D. (2009) · Cited by 1,094
Research works printed but not linked: 6
- Amrehn, 2017, Ui-net: Interactive Artificial Neural Networks for Iterative Image Segmentation Based on a User Model, Proc. Eurographics Workshop Vis. Comput. Biol. Med., 143
- Chen, 2018, Real-time 2d/3d Registration of Vertebra via Machine Learning and Geometric Transformation, Zidonghua Xuebao/Acta Automatica Sinica, 44, 1183
- Miao, Real-time 2d/3d Registration via Cnn Regression, 1430
- 2021, Artificial Intelligence/machine Learning (Ai/ml)-based Software as a Medical Device (Samd) Action Plan
- Varnavas, Fully Automated 2d-3d Registration and Verification, Med. image Anal., 26, 108, 10.1016/j.media.2015.08.005 · DOI · Paper page
- Xiangqian, 2020, 2d/3d Medical Image Registration Using Convolutional Neural Network, Chin. J. Biomed. Eng., 39, 394
Cited by
Sorted by citations
Chen, J., Liu, Y., Wei, S., Bian, Z., Subramanian, S., Carass, A., Prince, J. L., & Du, Y. (2024) · Medical Image Analysis · doi:10.1016/j.media.2024.103385 · Cited by 209
Gao, C., Killeen, B. D., Hu, Y., Grupp, R. B., Taylor, R. H., Armand, M., & Unberath, M. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00629-1 · Cited by 123
“…images, as we do for the hip-imaging X-ray tasks, is a typical size in the literature 5,12,71–76 , and most of the existing work on developing machine learning solutions for intra-operative X-ray analysis tasks, such as 2D/3D registration, do not develop nor test their methods on any real data 13 .”
BackgroundSelf-citationLocal feature matching using deep learning: A survey
Xu, S., Chen, S., Xu, R., Wang, C., Lu, P., & Guo, L. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102344 · Cited by 107
“These approaches, unlike their traditional counterparts, do not require explicit functional mappings, allowing for more robust solutions to the registration challenge [211].”
BackgroundEvolution of Surgical Robot Systems Enhanced by Artificial Intelligence: A Review
Liu, Y., Wu, X., Sang, Y., Zhao, C., Wang, Y., Shi, B., & Fan, Y. (2024) · Advanced Intelligent Systems · doi:10.1002/aisy.202300268 · Cited by 112
Exploring Augmented Reality Integration in Diagnostic Imaging: Myth or Reality?
Lastrucci, A., Wandael, Y., Barra, A., et al. (2024) · Diagnostics · doi:10.3390/diagnostics14131333 · Cited by 60
“This comprehensive analysis not only identifies the key areas where AR is making significant strides, but also underscores the opportunities for future research and the hurdles that need to be addressed to fully leverage AR’s capabilities in digital imaging.”
BackgroundInfluential
Metadata
- Authors
- Unberath, M., Gao, C., Hu, Y., Judish, M., Taylor, R. H., Armand, M., & Grupp, R.
- Affiliations
- Johns Hopkins University (US)
- Venue
- Frontiers in Robotics and AI
- Publisher
- Frontiers Media SA
- Published
- 2021-08-30
- Volume
- 8
- Pages
- 716007-716007
- ISSN
- 2296-9144 (ISSN-L)
- PMC
- PMC8436154
- OpenAlex
- W3190313291
- Semantic Scholar
- dfe6d3fb6e7c41a6d23df7ffb26dd759012409cc
- Cited by
- 102
- References
- 131
- Citations by year
- 2026: 19 · 2025: 23 · 2024: 33 · 2023: 17 · 2022: 9 · 2021: 1
- FWCI
- 2.14
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Frontiers in Robotics and AI (publishedVersion, cc-by)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- PubMed Central (submittedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- arXiv (Cornell University) (cc-by)
- Funders
- National Institute of Biomedical Imaging and Bioengineering (R21 EB028505)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Physical Sciences › Engineering › Biomedical Engineering › Anatomy and Medical Technology
- Health Sciences › Medicine › Surgery › Surgical Simulation and Training
- Keywords
- 2D-3D registration, image-guided interventions, machine learning, image-based navigation, minimally invasive surgery, fluoroscopy, endoscopy, surgical navigation, open problems
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-14, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-14 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
